vkrot opened a new pull request #24218: [SPARK-27281][DStreams] Change the way latest kafka offsets are retrieved to consumer#endOffsets URL: https://github.com/apache/spark/pull/24218 ## What changes were proposed in this pull request? Change the way latest kafka offsets are retrieved in `latestOffsets` methods from ``` consumer#seekToEnd(tp) consumer#position(tp) ``` to ``` consumer#endOffsets(partitions) ``` This fixed the issue from corresponding jira issue. With existing code from time to time I get an error ``` java.lang.IllegalArgumentException: requirement failed: numRecords must not be negative at scala.Predef$.require(Predef.scala:224) at org.apache.spark.streaming.scheduler.StreamInputInfo.<init>(InputInfoTracker.scala:38) at org.apache.spark.streaming.kafka010.DirectKafkaInputDStream.compute(DirectKafkaInputDStream.scala:250) at org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1$$anonfun$apply$7.apply(DStream.scala:342) at org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1$$anonfun$apply$7.apply(DStream.scala:342) at scala.util.DynamicVariable.withValue(DynamicVariable.scala:58) at org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1.apply(DStream.scala:341) at org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1.apply(DStream.scala:341) at org.apache.spark.streaming.dstream.DStream.createRDDWithLocalProperties(DStream.scala:416) at org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1.apply(DStream.scala:336) at org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1.apply(DStream.scala:334) at scala.Option.orElse(Option.scala:289) at org.apache.spark.streaming.dstream.DStream.getOrCompute(DStream.scala:331) at org.apache.spark.streaming.dstream.ForEachDStream.generateJob(ForEachDStream.scala:48) at org.apache.spark.streaming.DStreamGraph$$anonfun$1.apply(DStreamGraph.scala:122) at org.apache.spark.streaming.DStreamGraph$$anonfun$1.apply(DStreamGraph.scala:121) at scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:241) at scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:241) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48) at scala.collection.TraversableLike$class.flatMap(TraversableLike.scala:241) at scala.collection.AbstractTraversable.flatMap(Traversable.scala:104) at org.apache.spark.streaming.DStreamGraph.generateJobs(DStreamGraph.scala:121) at org.apache.spark.streaming.scheduler.JobGenerator$$anonfun$3.apply(JobGenerator.scala:249) at org.apache.spark.streaming.scheduler.JobGenerator$$anonfun$3.apply(JobGenerator.scala:247) at scala.util.Try$.apply(Try.scala:192) at org.apache.spark.streaming.scheduler.JobGenerator.generateJobs(JobGenerator.scala:247) at org.apache.spark.streaming.scheduler.JobGenerator.org$apache$spark$streaming$scheduler$JobGenerator$$processEvent(JobGenerator.scala:183) at org.apache.spark.streaming.scheduler.JobGenerator$$anon$1.onReceive(JobGenerator.scala:89) at org.apache.spark.streaming.scheduler.JobGenerator$$anon$1.onReceive(JobGenerator.scala:88) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49) 19/01/29 13:10:00 ERROR apps.BusinessRuleEngine: Job failed. Stopping JVM java.lang.IllegalArgumentException: requirement failed: numRecords must not be negative at scala.Predef$.require(Predef.scala:224) at org.apache.spark.streaming.scheduler.StreamInputInfo.<init>(InputInfoTracker.scala:38) at org.apache.spark.streaming.kafka010.DirectKafkaInputDStream.compute(DirectKafkaInputDStream.scala:250) at org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1$$anonfun$apply$7.apply(DStream.scala:342) at org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1$$anonfun$apply$7.apply(DStream.scala:342) at scala.util.DynamicVariable.withValue(DynamicVariable.scala:58) at org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1.apply(DStream.scala:341) at org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1.apply(DStream.scala:341) at org.apache.spark.streaming.dstream.DStream.createRDDWithLocalProperties(DStream.scala:416) at org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1.apply(DStream.scala:336) at org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1.apply(DStream.scala:334) at scala.Option.orElse(Option.scala:289) at org.apache.spark.streaming.dstream.DStream.getOrCompute(DStream.scala:331) at org.apache.spark.streaming.dstream.ForEachDStream.generateJob(ForEachDStream.scala:48) at org.apache.spark.streaming.DStreamGraph$$anonfun$1.apply(DStreamGraph.scala:122) at org.apache.spark.streaming.DStreamGraph$$anonfun$1.apply(DStreamGraph.scala:121) at scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:241) at scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:241) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48) at scala.collection.TraversableLike$class.flatMap(TraversableLike.scala:241) at scala.collection.AbstractTraversable.flatMap(Traversable.scala:104) at org.apache.spark.streaming.DStreamGraph.generateJobs(DStreamGraph.scala:121) at org.apache.spark.streaming.scheduler.JobGenerator$$anonfun$3.apply(JobGenerator.scala:249) at org.apache.spark.streaming.scheduler.JobGenerator$$anonfun$3.apply(JobGenerator.scala:247) at scala.util.Try$.apply(Try.scala:192) at org.apache.spark.streaming.scheduler.JobGenerator.generateJobs(JobGenerator.scala:247) at org.apache.spark.streaming.scheduler.JobGenerator.org$apache$spark$streaming$scheduler$JobGenerator$$processEvent(JobGenerator.scala:183) at org.apache.spark.streaming.scheduler.JobGenerator$$anon$1.onReceive(JobGenerator.scala:89) at org.apache.spark.streaming.scheduler.JobGenerator$$anon$1.onReceive(JobGenerator.scala:88) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49) java.lang.IllegalArgumentException: requirement failed: numRecords must not be negative at scala.Predef$.require(Predef.scala:224) at org.apache.spark.streaming.scheduler.StreamInputInfo.<init>(InputInfoTracker.scala:38) at org.apache.spark.streaming.kafka010.DirectKafkaInputDStream.compute(DirectKafkaInputDStream.scala:250) at org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1$$anonfun$apply$7.apply(DStream.scala:342) at org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1$$anonfun$apply$7.apply(DStream.scala:342) at scala.util.DynamicVariable.withValue(DynamicVariable.scala:58) at org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1.apply(DStream.scala:341) at org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1$$anonfun$1.apply(DStream.scala:341) at org.apache.spark.streaming.dstream.DStream.createRDDWithLocalProperties(DStream.scala:416) at org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1.apply(DStream.scala:336) at org.apache.spark.streaming.dstream.DStream$$anonfun$getOrCompute$1.apply(DStream.scala:334) at scala.Option.orElse(Option.scala:289) at org.apache.spark.streaming.dstream.DStream.getOrCompute(DStream.scala:331) at org.apache.spark.streaming.dstream.ForEachDStream.generateJob(ForEachDStream.scala:48) at org.apache.spark.streaming.DStreamGraph$$anonfun$1.apply(DStreamGraph.scala:122) at org.apache.spark.streaming.DStreamGraph$$anonfun$1.apply(DStreamGraph.scala:121) at scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:241) at scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:241) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48) at scala.collection.TraversableLike$class.flatMap(TraversableLike.scala:241) at scala.collection.AbstractTraversable.flatMap(Traversable.scala:104) at org.apache.spark.streaming.DStreamGraph.generateJobs(DStreamGraph.scala:121) at org.apache.spark.streaming.scheduler.JobGenerator$$anonfun$3.apply(JobGenerator.scala:249) at org.apache.spark.streaming.scheduler.JobGenerator$$anonfun$3.apply(JobGenerator.scala:247) at scala.util.Try$.apply(Try.scala:192) at org.apache.spark.streaming.scheduler.JobGenerator.generateJobs(JobGenerator.scala:247) at org.apache.spark.streaming.scheduler.JobGenerator.org$apache$spark$streaming$scheduler$JobGenerator$$processEvent(JobGenerator.scala:183) at org.apache.spark.streaming.scheduler.JobGenerator$$anon$1.onReceive(JobGenerator.scala:89) at org.apache.spark.streaming.scheduler.JobGenerator$$anon$1.onReceive(JobGenerator.scala:88) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49) ``` With 10+ jobs consuming 100+ partitions this happens only once a day - once a week. The code seekToEnd returns offsets that are lower that `currentOffsets`, while `consumer#endOffsets` returns correct end offsets ## How was this patch tested? Existing tests
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
